Feasibility of synthetic computed tomography generated with an adversarial network for multi-sequence magnetic resonance-based brain radiotherapy

ABSTRACT The aim of this work is to generate synthetic computed tomography (sCT) images from multi-sequence magnetic resonance (MR) images using an adversarial network and to assess the feasibility of sCT-based treatment planning for brain radiotherapy. Datasets for 15 patients with glioblastoma were selected and 580 pairs of CT and MR images were used. T1-weighted, T2-weighted and fluid-attenuated inversion recovery MR sequences were combined to create a three-channel image as input data. A conditional generative adversarial network (cGAN) was trained using image patches. The image quality was evaluated using voxel-wise mean absolute errors (MAEs) of the CT number. For the dosimetric evaluation, 3D conformal radiotherapy (3D-CRT) and volumetric modulated arc therapy (VMAT) plans were generated using the original CT set and recalculated using the sCT images. The isocenter dose and dose–volume parameters were compared for 3D-CRT and VMAT plans, respectively. The equivalent path length was also compared. The mean MAEs for the whole body, soft tissue and bone region were 108.1 ± 24.0, 38.9 ± 10.7 and 366.2 ± 62.0 hounsfield unit, respectively. The dosimetric evaluation revealed no significant difference in the isocenter dose for 3D-CRT plans. The differences in the dose received by 2% of the volume (D2%), D50% and D98% relative to the prescribed dose were <1.0%. The overall equivalent path length was shorter than that for real CT by 0.6 ± 1.9 mm. A treatment planning study using generated sCT detected only small, clinically negligible differences. These findings demonstrated the feasibility of generating sCT images for MR-only radiotherapy from multi-sequence MR images using cGAN.

Download Full-text

Faculty Opinions recommendation of Whole-body magnetic resonance imaging and positron emission tomography-computed tomography in oncology.

Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature ◽

10.3410/f.718386647.793495257 ◽

2014 ◽

Author(s):

Jean-Pascal Machiels

Keyword(s):

Magnetic Resonance Imaging ◽

Computed Tomography ◽

Positron Emission Tomography ◽

Magnetic Resonance ◽

Emission Tomography ◽

Whole Body ◽

Resonance Imaging ◽

Positron Emission ◽

Body Magnetic Resonance Imaging

Download Full-text

Pseudo-Computed Tomography Generation Using Rigid Registration of Pretaken Diagnostic Computed Tomography to Planning Magnetic Resonance for Magnetic Resonance–Based Treatment Planning

International Journal of Radiation Oncology*Biology*Physics ◽

10.1016/j.ijrobp.2016.06.2289 ◽

2016 ◽

Vol 96 (2) ◽

pp. E663

Author(s):

H.J. Jeong ◽

K.M. Kang ◽

B.K. Jeong ◽

J.H. Song ◽

Y.H. Lee ◽

...

Keyword(s):

Computed Tomography ◽

Magnetic Resonance ◽

Treatment Planning ◽

Rigid Registration

Download Full-text

Computed tomography and magnetic resonance imaging of the whole body. 3rd ed, 2 vols Edited by John R. Haaga, MD, Charles Lanzieri, MD, David J. Sartoris, MD, Ellas A. Zerhouni, MD St Louis, Mo: Mosby-Year Book, 1994. $275.00: pp 1,800; 4,082 figures

Journal of Magnetic Resonance Imaging ◽

10.1002/jmri.1880050206 ◽

1995 ◽

Vol 5 (2) ◽

pp. 150-150

Author(s):

Sanjay Saini

Keyword(s):

Magnetic Resonance Imaging ◽

Computed Tomography ◽

Magnetic Resonance ◽

Whole Body ◽

Resonance Imaging

Download Full-text

Agreement of Magnetic Resonance Imaging With Computed Tomography in the Assessment for Acute Skull Fractures in a Canine and Feline Cadaver Model

Frontiers in Veterinary Science ◽

10.3389/fvets.2021.603775 ◽

2021 ◽

Vol 8 ◽

Author(s):

Silke Hecht ◽

Kimberly M. Anderson ◽

Aude Castel ◽

John F. Griffin ◽

Adrien-Maxence Hespel ◽

...

Keyword(s):

Magnetic Resonance Imaging ◽

Computed Tomography ◽

Magnetic Resonance ◽

Head Trauma ◽

Imaging Modality ◽

Small Animal ◽

Skull Fractures ◽

Resonance Imaging ◽

Significant Difference ◽

Mri Sequences

Computed tomography (CT) is the imaging modality of choice to evaluate patients with acute head trauma. However, magnetic resonance imaging (MRI) may be chosen in select cases. The objectives of this study were to evaluate the agreement of MRI with CT in the assessment for presence or absence of acute skull fractures in a canine and feline cadaver model, compare seven different MRI sequences (T1-W, T2-W, T2-FLAIR, PD-W, T2*-W, “SPACE” and “VIBE”), and determine agreement of four different MRI readers with CT data. Pre- and post-trauma CT and MRI studies were performed on 10 canine and 10 feline cadaver heads. Agreement of MRI with CT as to presence or absence of a fracture was determined for 26 individual osseous structures and four anatomic regions (cranium, face, skull base, temporomandibular joint). Overall, there was 93.5% agreement in assessing a fracture as present or absent between MRI and CT, with a significant difference between the pre and post trauma studies (99.4 vs. 87.6%; p < 0.0001; OR 0.042; 95% CI 0.034–0.052). There was no significant difference between dogs and cats. The agreement for the different MRI sequences with CT ranged from 92.6% (T2*-W) to 94.4% (PD-W). There was higher agreement of MRI with CT in the evaluation for fractures of the face than other anatomic regions. Agreement with CT for individual MRI readers ranged from 92.6 to 94.7%. A PD-W sequence should be added to the MR protocol when evaluating the small animal head trauma patient.

Download Full-text

Role of whole-body 64-slice multidetector computed tomography in treatment planning for multiple myeloma

La radiologia medica ◽

10.1007/s11547-012-0880-0 ◽

2012 ◽

Vol 118 (5) ◽

pp. 799-805 ◽

Cited By ~ 10

Author(s):

Ahmed Abdel Khalek Abdel Razek ◽

Amany Ezzat ◽

Emad Azmy ◽

Nehal Tharwat

Keyword(s):

Computed Tomography ◽

Multiple Myeloma ◽

Multidetector Computed Tomography ◽

Treatment Planning ◽

Whole Body

Download Full-text

High resolution computed tomography and magnetic resonance imaging in the pre-operative assessment of cochlear implant patients

The Journal of Laryngology & Otology ◽

10.1258/002221503322334495 ◽

2003 ◽

Vol 117 (9) ◽

pp. 692-695 ◽

Cited By ~ 26

Author(s):

T. G. Gleeson ◽

P. D. Lacy ◽

M. Bresnihan ◽

R. Gaffney ◽

P. Brennan ◽

...

Keyword(s):

Computed Tomography ◽

Magnetic Resonance ◽

Cochlear Implant ◽

High Resolution Computed Tomography ◽

Time Of Surgery ◽

Surgical Access ◽

Significant Difference ◽

Mri Scans ◽

Operative Assessment ◽

Ct And Mri

Optimal imaging protocols for cochlear implantation have yet to be determined. Pre-operative computed tomography (CT) and magnetic resonance image (MRI) scans are used to assess cochlear anatomy and patency, to delineate surgical access, and to aid in choice of side for implantation. However, opinion still differs as to which modality provides more information in pre-operative assessment, or if, indeed, a combination of the two is superior.The first 88 patients on the Irish National Cochlear Implant Programme (NCIP) were retrospectively studied to determine the accuracy of pre-operative CT and MRI in predicting abnormalities at the time of surgery. Correlation with surgical findings was determined in three separate groups of patients (those who had CT only, those who had MRI only, and those who had both CT and MRI performed).Of the 24 patients that had both CT and MRI performed, both modalities had a 79 per cent correlation with surgical findings. CT and MRI reports concurred in 75 per cent of cases. Specificity and negative predictive value were high (86 per cent and 90 per cent, respectively). CT alone (47 cases) correlated with surgery in 39 cases (83 per cent); MRI alone (17 cases) correlated in 15 cases (88 per cent).The findings of this study suggest that CT and MRI are effective at predicting normal inner ear anatomy, and thus at predicting the patient and the cochlea most suitable for implantation. Both modalities are useful in determining the side of implantation, thus avoiding potential surgical difficulties in cases of unilateral abnormalities. There was no significant difference between the ability of MRI and CT to detect abnormalities at the time of surgery. In this series the combination of CT and MRI has not been shown to be superior to either modality used alone, although anecdotal evidence to the contrary was noted.

Download Full-text

Prospective, blinded trial of whole-body magnetic resonance imaging versus computed tomography positron emission tomography in staging primary and recurrent cancer of the head and neck

The Journal of Laryngology & Otology ◽

10.1017/s0022215110001398 ◽

2010 ◽

Vol 124 (12) ◽

pp. 1274-1277 ◽

Cited By ~ 6

Author(s):

J P O'Neill ◽

M Moynagh ◽

E Kavanagh ◽

T O'Dwyer

Keyword(s):

Magnetic Resonance Imaging ◽

Computed Tomography ◽

Positron Emission Tomography ◽

Magnetic Resonance ◽

Head And Neck ◽

Emission Tomography ◽

Whole Body ◽

Resonance Imaging ◽

Positron Emission ◽

Body Magnetic Resonance Imaging

AbstractObjectives:To compare the use of computed tomography – positron emission tomography and whole-body magnetic resonance imaging for the staging of head and neck cancer.Patients and methods:From January to July 2009, 15 consecutive head and neck cancer patients (11 men and four women; mean age 59 years; age range 19 to 81 years) underwent computed tomography – positron emission tomography and whole-body magnetic resonance imaging for pre-therapeutic evaluation. All scans were staged, as per the American Joint Committee on Cancer tumour–node–metastasis classification, by two blinded consultant radiologists, in two sittings. Diagnoses were confirmed by histopathological examination of endoscopic biopsies, and in some cases whole surgical specimens.Results:Tumour staging showed a 74 per cent concordance, node staging an 80 per cent concordance and metastasis staging a 100 per cent concordance, comparing the two imaging modalities.Conclusion:This study found radiological staging discordance between the two imaging modalities. Whole-body magnetic resonance imaging is an emerging staging modality with superior visualisation of metastatic disease, which does not require exposure to ionising radiation.

Download Full-text